Tehran University of Medical Sciences Frontiers in Biomedical Technologies 2345-5837 10 2 2023 02 25 169 179 EN Sepideh Amiri b) Department of Computer Sciences, University of Copenhagen, Copenhagen, Denmark Mina Akbarabadi Department of Information Technology, Faculty of Industrial Engineering, K. N. Toosi University of Technology, Tehran, Iran Shahnaz Rimaz d) Radiation Biology Research Center, Iran University of Medical Sciences, Tehran, Iran Fatemeh Abdolali c) Department of radiology and diagnostic imaging, faculty of medicine and dentistry, Alberta University, Edmonton, AB, Canada Reza Ahadi f) Department of anatomical science Iran University of medical science Tehran. Iran Mohsen Afshani Department of Electrical and Computer Engineering, Tarbiat Modares University, Tehran, Iran Zahra alaei askarabad Department of Radiation sciences, Allied medicine faculty, Iran University of Medical Sciences, Tehran, Iran Tahereh Kowsarirad h) Department of Radiation sciences, Allied medicine faculty, Iran University of Medical Sciences, Tehran, Iran Sohrab Sakinehpour Department of Radiation sciences, Allied medicine faculty, Iran University of Medical Sciences, Tehran, Iran Nazila Eyvazzadeh Radiation Sciences Research Center, AJA University of medical sciences, Tehran, Iran Susan Cheraghi Assistant Professor Faculty of Para-medicine, IUMS, Tehran, Iran 2022 01 14 2022 05 30 Purpose: Diagnosis of musculoskeletal abnormalities is essential due to more than 1.7 billion people worldwide being affected by musculoskeletal disorders. In this study, we focus on diagnosing musculoskeletal abnormalities in the lower extremities within X-ray images by deep architecture neural networks. Methods: Our dataset contains 61,098 musculoskeletal radiographic images, which includes 42658 normal images and 18440 abnormal images. Each image belongs to a single type of lower extremity radiography, including the toe, foot, ankle, leg, knee, femur, and hip joint. We proposed a new deep neural network architecture with two different scenarios that perform lower extremity lesion diagnosis functions with high accuracy. The core of the proposed method is a deep learning framework based on the Mask R-CNN and CNN. The model with the best results utilized the Mask R-CNN algorithm to generate the bounding box, followed by the CNN algorithm to detect the class based on that. Results: The proposed model can detect different types of lower limb lesions by an AUC-ROC of 0.925, with an operating point of 0.859 sensitivity and a specificity of 0.893. Conclusions: By comparing the different results, it can be concluded that the consecutive implementation of Mask R-CNN and CNN function better than Mask R-CNN and CNN separately. https://fbt.tums.ac.ir/index.php/fbt/article/view/449 https://fbt.tums.ac.ir/index.php/fbt/article/download/449/309